Skip to main content
Glama
Sign In
neshan-mcp

neshan-mcp

by sepehr071
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Search places on Neshan

ns_search
Read-onlyIdempotent

Find places, businesses, streets, and squares on the Neshan map by name or category near a city or point, and geocode names or addresses to coordinates for routing.

Instructions

Find places, businesses, streets and squares on the Neshan map by name or category near a city or point.

Also geocodes a name or address to coordinates before ns_route. Results have id (for ns_place, ns_reviews; streets and areas have none), name, category, address, lat/lng, distance_m from near, rating, votes, status (باز است = open now) and phone. Sponsored results are left out. Nothing found: try a shorter or Persian query.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "ns_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
nearNoCity name ('Tehran', 'شیراز') or point 'lat,lng' to rank results by closeness to.Tehran
limitNoMax results (1-30).
queryYesPlace name, category, street or square, Persian or English, e.g. 'کافه لمیز', 'پمپ بنزین', 'میدان ونک'.
open_nowNoOnly places open now (24-hour included).
min_ratingNoOnly places rated at least this (1-5).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare it as a safe, idempotent, open-world read. The description goes well beyond that: it enumerates returned fields, notes that streets and areas lack an `id` (so ns_place/ns_reviews cannot be chained), explains that `distance_m` is relative to `near`, decodes the Persian status value, and states that sponsored results are excluded.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The capability and scope are front-loaded in one sentence, and the return-field inventory is compactly packed into a second. It is dense to the point of being telegraphic ("streets and areas have none"), which costs a little readability but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly supplies the return shape, filter behavior, and empty-result handling, which is the right load for a 5-parameter search tool. A minor gap remains: the geocoding path is mentioned but the description never says what is returned when no place matches, only that coordinates can be produced.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and every parameter already carries its own description, including the `near` city-or-'lat,lng' form and the 1-30 limit range. The description adds only the indirect point that `distance_m` is measured from `near`, which reframes but does not extend the schema's parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific verb (find) and an explicit resource set (places, businesses, streets, squares) plus its scope (by name or category, near a city or point). It also flags a second capability (geocoding a name/address to coordinates before ns_route), which lets an agent separate it from ns_nearby and ns_reverse_geocode without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Geocodes a name or address to coordinates before ns_route" states a concrete downstream use, and "Nothing found: try a shorter or Persian query" supplies recovery guidance. It stops short of explicitly excluding alternatives (e.g., when to prefer ns_nearby or ns_reverse_geocode instead), so no exclusions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools